Kyoungseob Shin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kyoungseob Shin has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Sunghoon Kwon
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Republic of Korea
3 shared publications Hyunho Lee
Seoul National University
2 shared publicationsYongju Lee
Seoul National University
2 shared publications- Haewook Jang
Interdisciplinary Program in Bioengineering, Seoul National University, Seoul 08826, Korea
1 shared publication - Juhong Nam
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Korea
1 shared publication - Jungil Choi
Department of Mechanical Engineering, Ajou University, Suwon, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (4) , 5160-5168
GRIP: Graph Representation of Immune Repertoire Using Graph Neural Network and Transformer
The immune repertoire is a collection of immune recep-tors that has emerged as an important biomarker for both diagnostic and therapeutic of cancer patients. In terms of deep learning, analyzing immune repertoire is a challeng-ing multiple-instance learning problem in which the im-mune repertoire of an individual is a bag, and the immune receptor is an instance. Although several deep learning methods for immune repertoire analysis are introduced, they consider the immune repertoire as a set-like struc-ture that doesn’t take account of the nature of the im-mune response. When the immune response occurs, mu-tations are introduced to the immune receptor sequence sequentially to optimize the immune response against the pathogens that enter our body. As a result, immune receptors for the specific pathogen have the lineage of evolution; thus, immune repertoire is better represented as a graph-like structure. In this work, we present our novel method graph representation of immune repertoire (GRIP), which analyzes the immune repertoire as a hier-archical graph structure and utilize the collection of graph neural network followed by graph pooling and transformer to efficiently represents the immune reper-toire as an embedding vector. We show that GRIP predict the survival probability of cancer patients better than the set-based methods and graph-based structure is critical for performance. Also, GRIP provides interpretable re-sults, which prove that GRIP adequately use the progno-sis-related immune receptor and give further possibility to use the GRIP as the novel biomarker searching tool
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (4) , 5160-5168
Open AccessGRIP: Graph Representation of Immune Repertoire Using Graph Neural Network and Transformer
The immune repertoire is a collection of immune recep-tors that has emerged as an important biomarker for both diagnostic and therapeutic of cancer patients. In terms of deep learning, analyzing immune repertoire is a challeng-ing multiple-instance learning problem in which the im-mune repertoire of an individual is a bag, and the immune receptor is an instance. Although several deep learning methods for immune repertoire analysis are introduced, they consider the immune repertoire as a set-like struc-ture that doesn’t take account of the nature of the im-mune response. When the immune response occurs, mu-tations are introduced to the immune receptor sequence sequentially to optimize the immune response against the pathogens that enter our body. As a result, immune receptors for the specific pathogen have the lineage of evolution; thus, immune repertoire is better represented as a graph-like structure. In this work, we present our novel method graph representation of immune repertoire (GRIP), which analyzes the immune repertoire as a hier-archical graph structure and utilize the collection of graph neural network followed by graph pooling and transformer to efficiently represents the immune reper-toire as an embedding vector. We show that GRIP predict the survival probability of cancer patients better than the set-based methods and graph-based structure is critical for performance. Also, GRIP provides interpretable re-sults, which prove that GRIP adequately use the progno-sis-related immune receptor and give further possibility to use the GRIP as the novel biomarker searching tool
- Open Access
GRIP: Graph Representation of Immune Repertoire Using Graph Neural Network and Transformer
The immune repertoire is a collection of immune receptors that has emerged as an important biomarker for both the diagnostic and therapeutic of cancer patients. In terms of deep learning, analyzing immune repertoire is a challenging multiple-instance learning problem in which the immune repertoire of an individual is a bag, and the immune receptor is an instance. Although several deep learning methods for immune repertoire analysis are introduced, they consider the immune repertoire as a set-like structure that doesn’t take into account the nature of the immune response. When the immune response occurs, mutations are introduced to the immune receptor sequence sequentially to optimize the immune response against the pathogens that enter our body. As a result, immune receptors for the specific pathogen have the lineage of evolution; thus, the immune repertoire is better represented as a graph-like structure. In this work, we present our novel method, graph representation of immune repertoire (GRIP), which analyzes the immune repertoire as a hierarchical graph structure and utilize the collection of graph neural network followed by graph pooling and transformer to efficiently represents the immune repertoire as an embedding vector. We show that GRIP predicts the survival probability of cancer patients better than the set-based methods, and graph-based structure is critical for performance. Also, GRIP provides interpretable results, which prove that GRIP adequately uses the prognosis-related immune receptor and gives the further possibility to use the GRIP as the novel biomarker searching tool.
Open AccessGRIP: Graph Representation of Immune Repertoire Using Graph Neural Network and Transformer
The immune repertoire is a collection of immune receptors that has emerged as an important biomarker for both the diagnostic and therapeutic of cancer patients. In terms of deep learning, analyzing immune repertoire is a challenging multiple-instance learning problem in which the immune repertoire of an individual is a bag, and the immune receptor is an instance. Although several deep learning methods for immune repertoire analysis are introduced, they consider the immune repertoire as a set-like structure that doesn’t take into account the nature of the immune response. When the immune response occurs, mutations are introduced to the immune receptor sequence sequentially to optimize the immune response against the pathogens that enter our body. As a result, immune receptors for the specific pathogen have the lineage of evolution; thus, the immune repertoire is better represented as a graph-like structure. In this work, we present our novel method, graph representation of immune repertoire (GRIP), which analyzes the immune repertoire as a hierarchical graph structure and utilize the collection of graph neural network followed by graph pooling and transformer to efficiently represents the immune repertoire as an embedding vector. We show that GRIP predicts the survival probability of cancer patients better than the set-based methods, and graph-based structure is critical for performance. Also, GRIP provides interpretable results, which prove that GRIP adequately uses the prognosis-related immune receptor and gives the further possibility to use the GRIP as the novel biomarker searching tool.
- Open Access
- 19 August 2021
- Published by MDPI AG in Biosensors
- Vol. 11 (8) , 283
Color-Coded Droplets and Microscopic Image Analysis for Multiplexed Antibiotic Susceptibility Testing
Since the discovery of antibiotics, the emergence of antibiotic resistance has become a global issue that is threatening society. In the era of antibiotic resistance, finding the proper antibiotics through antibiotic susceptibility testing (AST) is crucial in clinical settings. However, the current clinical process of AST based on the broth microdilution test has limitations on scalability to expand the number of antibiotics that are tested with various concentrations. Here, we used color-coded droplets to expand the multiplexing of AST regarding the kind and concentration of antibiotics. Color type and density differentiate the kind of antibiotics and concentration, respectively. Microscopic images of a large view field contain numbers of droplets with different testing conditions. Image processing analysis detects each droplet, decodes color codes, and measures the bacterial growth in the droplet. Testing E. coli ATCC 25922 with ampicillin, gentamicin, and tetracycline shows that the system can provide a robust and scalable platform for multiplexed AST. Furthermore, the system can be applied to various drug testing systems, which require several different testing conditions.
- 19 August 2021
- Published by MDPI AG in Biosensors
- Vol. 11 (8) , 283
Open AccessColor-Coded Droplets and Microscopic Image Analysis for Multiplexed Antibiotic Susceptibility Testing
Since the discovery of antibiotics, the emergence of antibiotic resistance has become a global issue that is threatening society. In the era of antibiotic resistance, finding the proper antibiotics through antibiotic susceptibility testing (AST) is crucial in clinical settings. However, the current clinical process of AST based on the broth microdilution test has limitations on scalability to expand the number of antibiotics that are tested with various concentrations. Here, we used color-coded droplets to expand the multiplexing of AST regarding the kind and concentration of antibiotics. Color type and density differentiate the kind of antibiotics and concentration, respectively. Microscopic images of a large view field contain numbers of droplets with different testing conditions. Image processing analysis detects each droplet, decodes color codes, and measures the bacterial growth in the droplet. Testing E. coli ATCC 25922 with ampicillin, gentamicin, and tetracycline shows that the system can provide a robust and scalable platform for multiplexed AST. Furthermore, the system can be applied to various drug testing systems, which require several different testing conditions.